# Research Papers — 2026-06 · bundle page 32 of 260 > Full-text markdown of papers #1551–1600 of 12993 published in 2026-06, newest first. AI-readable mirrors of the full 12993-paper 2026-06 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-06/page/32 [← Previous bundle](https://aipod.dev/papers/archive/2026-06/page/31.md) [Next bundle →](https://aipod.dev/papers/archive/2026-06/page/33.md) ### DriftGuard: Safety-Aware Multi-Monitor Detection and Selective Adaptation for Evolving Toxicity Moderation Authors: Yuting Xin, Hanyu Cai, Binqi Shen, Lier Jin, Lan Hu Published: 2026-06-27 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.28725v1 Automated toxicity moderation systems operate in dynamic online environments where harmful behavior evolves through coded language, shifting targets, and strategic adaptation to enforcement. Existing drift detection methods often focus on global distributional change, but such signals may miss safety-relevant shifts that emerge in localized harm subspaces or high-risk model-error regions. This paper introduces DriftGuard, a safety-aware adaptive moderation framework that combines multi-monitor drift detection with selective model updating. The framework tracks global text drift, identity-harm drift, model uncertainty, toxic-risk drift, and false-negative-risk drift. When safety-relevant change is detected, the model is updated using a hard-mix adaptation set that prioritizes likely false negatives, identity-related high-risk examples, false-positive-risk examples, and uncertain boundary cases. Experiments on Civil Comments temporal shift and Jigsaw-to-DynaHate cross-dataset shift show that safety-aware monitors detect risks missed by global drift alone. Hard-mix adaptation improves toxic recall and accuracy over no-update and random-balanced baselines, raising toxic recall to 0.8777 on Civil Comments and from 0.7107 to 0.8523 on DynaHate. Bootstrap analysis further shows stable DynaHate safety gains, with toxic recall increasing by 0.1418 and false-negative prevalence decreasing by 0.0781. Overall, DriftGuard links safety-aware drift detection to targeted, lightweight model updating for more robust adaptive toxicity moderation. --- ### CCRC: A Change-Aware Captioning and Reasoning Chain for Image Change Captioning and Segmentation Authors: Jinhong Hu, Xiaoping Wang, Shuyin Huang, Guojin Zhong, Kaitai Liu, Kai Lu Published: 2026-06-27 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.28724v1 Understanding and localizing subtle changes between paired images is critical for tasks such as surveillance and image editing. However, traditional Image Change Captioning (ICC) methods lack spatial grounding, limiting their precision. We introduce Image Change Captioning and Segmentation (ICCS), a new multimodal task that jointly requires structured change description and pixel-level localization. To address ICCS, we propose the Change-aware Captioning and Reasoning Chain (CCRC), a dual-chain framework that decouples semantic reasoning from spatial segmentation. The first chain, Chain-of-Change-Captioning (CCC), enhances fine-grained change perception via a visual fusion module based on Multi-Head Change-aware Attention inserted between the visual and language components of a Multimodal Large Language Model (MLLM). CCC also determines whether a change is segmentable. If not, it alone generates the caption. Otherwise, the second chain, Chain-of-Change-Segmenting (CCS), is activated, leveraging spatial priors from CCC and refining masks with a Change-aware Token Refiner for accurate boundary localization. We evaluate CCRC on both synthetic and real-world change detection benchmarks with pixel-level supervision. Experiments show CCRC achieves state-of-the-art performance. --- ### ComMem: Complementary Memory Systems for Test-Time Adaptation of Vision-Language Models Authors: Guanglong Sun, Shuang Cui, Bo Lei, Liyuan Wang, Zihan Zhai, Hongwei Yan, Hang Su, Jun Zhu, Yi Zhong Published: 2026-06-27 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.28719v1 Test-time adaptation (TTA) of vision-language models (VLMs) is essential for their robust deployment in dynamic, real-world environments. However, existing TTA methods often adapt locally without accumulating knowledge over time, or operating within a single modality without exploiting VLMs' inherently multi-modal nature. Inspired by the \textbf{Com}plementary \textbf{Mem}ory systems of the biological brain, we propose \textbf{ComMem}, an innovative approach that mimics the distinct but cooperative roles of the hippocampus and neocortex to enable effective TTA for VLMs. ComMem consists of two key components: a fast-adapting detailed memory, akin to the hippocampus, that forms a dynamic visual cache from high-confidence test samples; and a slow-integrating abstract memory, akin to the neocortex, that continually refines global textual prototypes. For each test instance, ComMem jointly optimizes both memory systems to ensure cross-modal consistency. Extensive experiments on 15 benchmark datasets show that ComMem significantly outperforms state-of-the-art methods under both natural distribution shifts and cross-dataset generalization, offering a promising direction for enhancing VLMs' practical adaptability. --- ### TrajRS: Towards Certified Robustness in Pedestrian Trajectory Prediction Authors: Liang Zhang, Gaojie Jin, Yao Shi, Quanzhi Li, Cheng-Chao Huang, David N. Jansen, Lijun Zhang Published: 2026-06-27 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.28716v1 The robustness of trajectory prediction models is crucial for developing safe autonomous driving systems. Adversarial attacks on trajectory prediction can significantly impair the accuracy of predicted trajectories, leading to hazardous driving behaviors. While heuristic defense strategies have been implemented to enhance the robustness of trajectory prediction models, these measures often fail against more sophisticated, targeted adversarial attacks. Hence, there is a pressing need to establish verifiable safety assurances for trajectory prediction models. In this paper, we extend the traditional Randomized Smoothing framework to "TrajRS", which provides a certified robust radius for smoothed trajectory predictors. We clarify and expand the formal definitions of robustness in trajectory prediction and tailor the practical TrajRS scheme specifically to "robustness for the optimal prediction" and "robustness for all possible predictions". An extensive set of experiments demonstrates that TrajRS effectively achieves robustness certification for all smoothed pedestrian trajectory predictors in this work. --- ### SEATauBench: Progressively Adapting Tool-Agent-User Evaluation Into Low-Resource Southeast Asian Languages Authors: My Chiffon Nguyen, Aulia Adila, Saksorn Ruangtanusak, Kittiphat Leesombatwathana, Vissuta Gunawan Lim, Patomporn Payoungkhamdee, Samuel Cahyawijaya Published: 2026-06-27 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2606.28715v2 While AI development and evaluation for Southeast Asia (SEA) has grown rapidly, agent capabilities in regional languages are still poorly understood despite its importance to sovereign AI. To fill this gap, we introduce SEATauBench, the first agent-focused evaluation framework for SEA sovereign AI. It adapts Tau2-Bench to five languages---Mandarin, Vietnamese, Thai, Indonesian, and Filipino---and evaluates agents across progressively localized settings that vary the language of user-agent interaction, tool specifications, and task domains. Across three models, we find that English agent capabilities transfer reasonably well when only the conversation language changes, but quality and robustness degrade sharply as more task contexts are localized, with the largest losses in full domain adaptation. We also highlight the limits of English-only agent assessment for predicting agent capabilities in SEA languages. More broadly, SEATauBench provides a diagnostic benchmark and reusable adaptation pipeline for building reliable multilingual agents for linguistically diverse regions. Data and code can be accessed at github.com/SEACrowd/SEATauBench --- ### SEATauBench: Adapting Tool-Agent-User Evaluation Into Low-Resource Southeast Asian Languages Authors: My Chiffon Nguyen, Aulia Adila, Saksorn Ruangtanusak, Kittiphat Leesombatwathana, Vissuta Gunawan Lim, Patomporn Payoungkhamdee, Samuel Cahyawijaya Published: 2026-06-27 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2606.28715v1 While AI development and evaluation for Southeast Asia (SEA) has grown rapidly, agent capabilities in regional languages are still poorly understood despite its importance to sovereign AI. To fill this gap, we introduce SEATauBench, the first agent-focused evaluation framework for SEA sovereign AI. SeaTau adapts TauBench to five languages -- Mandarin, Vietnamese, Thai, Indonesian, and Filipino -- and evaluates agents across progressively localized settings that vary the language of user-agent interaction, tool specifications, and task domains. Across three recent models, we find that English agent capabilities transfer reasonably well when only the conversation language changes, but quality and robustness degrade sharply as more task contexts are localized, with the largest losses in full domain adaptation. We also the limits of English-only agent assessment for measuring agent capabilities in SEA languages. More broadly, SeaTau provides a diagnostic benchmark and reusable adaptation pipeline for building reliable multilingual agents for linguistically diverse regions. Data and code can be accessed at github.com/SEACrowd/SEATauBench. --- ### J-LAW: Joint Localization and Action-Conditioned World Modeling via Coupled Latent Factor Graphs Authors: Guanqun Cao, Liang Chen Published: 2026-06-27 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2606.28712v2 Classical simultaneous localization and mapping (SLAM) estimates metric poses and a geometric map but does not provide an action-conditioned predictive state. Action-conditioned world models learn compact latent dynamics but ignore global metric consistency and accumulate drift under open-loop rollout. We introduce J-LAW (Joint Localization and Action-Conditioned World Modeling), a unified factor-graph formulation that connects metric pose variables, predictive latent states, and persistent latent landmarks in this letter.J-LAW represents each image as a compact predictive state and combines it with pose or motion measurements through a separately learned mapping. Its maximum a posteriori (MAP) factor graph enforces consistency between these complementary sources of information over time. Experiments on PushT and WildGS show that J-LAW's factor-graph representation can improve long-horizon latent consistency and recover more reliable predictive states under partial observations, forming a foundation for future integrated localization and planning systems. --- ### J-LAW: Joint Localization and Actionable World Modeling via Coupled Latent Factor Graphs Authors: Guanqun Cao, Liang Chen Published: 2026-06-27 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2606.28712v1 Classical SLAM estimates metric poses and a geometric map but produces no actionable predictive model for planning. Action-conditioned world models learn compact latent dynamics for planning but ignore global metric consistency and accumulate drift under open-loop rollout. We argue these are two views of the same estimation problem and propose J-LAW (Joint Localization and Actionable World Modeling) in this letter: a coupled factor graph that jointly optimizes metric object poses, latent world states, and latent landmark embeddings. The bridge is a pose-conditioned latent encoder and a learned pose--latent coupling factor, so that better localization improves the world model and vice versa. We cast observation, action-conditioned prediction, metric odometry, pose--latent coupling, latent loop closure, and latent landmark observation as probabilistic factors in a single MAP objective. Real-data experiments on PushT and WildGS show that coupled graph correction substantially reduces latent prediction RMSE and endpoint drift relative to open-loop rollout, while latent loop closure improves global trajectory consistency. J-LAW yields a map that is simultaneously metric (poses) and actionable (latent landmarks for planning). --- ### The Two Genie Game: Adoption and Welfare in Audit-Grounded AI Governance Authors: Darrell Lewis-Sandy Published: 2026-06-27 Categories: cs.AI, cs.GT arXiv: https://arxiv.org/abs/2606.28710v1 We ask under what conditions an agent with a harm-minimizing policy can displace an approval-seeking (RLHF) agent in a competitive market, and when that policy is sufficient to prevent community harm. We use evolutionary game theory (finite-population Moran-Fermi pairwise comparison) to formalize this subject to assumptions of wisher hindsight, peer testimony, a monotone harm ledger, sufficient information density of community feedback, and a finite, depleting resource pool, in a negative-sum environment. We show that adoption is favored when the prior distributions on how readily wishers attune to community sentiment are monotone, exhibit endpoint inversion, and have a centro-symmetric pairing property, and demonstrate this with several long-tailed priors (Hill, Pareto, Lomax, Frechet). Where it is favored, a critical adoption level separates communities that drift back to the approval-seeking agent from those for which the audited agent fixes; above that level fixation is the overwhelmingly likely outcome. We derive when fixation is attainable as a bound on the effective (informational) size N_c of the community, which must be small enough to allow fixation before depletion. We present these as Theorems 5.4 and 5.5; the algebraic and finite-grid backbone is machine-checked in Lean 4, with the barrier-crossing asymptotics retained as explicit hypotheses. We show that a self-audited agent with a community ledger is not, in general, sufficient to prevent community harm. Sufficiency depends both upon the alignment of the agent's audit with community values and the timeframe over which harm is evaluated. Regardless of alignment, once adoption reaches dominance, the state is absorbing. The same policy that reduced harm under alignment becomes a trap, welfare-negative under misalignment and, even under alignment, one that locks in harm deferred past the adoption horizon. --- ### AnTenA: Actionable and Explainable Tensor Analysis System with Large Language Models Authors: Dawon Ahn, Auder Der, Evangelos E. Papalexakis Published: 2026-06-27 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2606.28708v1 Accurately explaining hidden patterns in multi-aspect data has typically been done by leveraging labels and/or accompanying auxiliary metadata. However, labels and auxiliary data may be inaccurate (e.g. nonstandard, inconsistent), insufficient (e.g. static tabular metadata for time-dependent recordings), or unavailable. % We propose \fullmethod (\method), which leverages the knowledge of large language models (LLMs) to explain the hidden patterns in human narratives. \method uses task-agnostic and task-specific prompts to explain extracted co-clustered latent patterns from tensor decomposition. To evaluate these explanations, we test the LLMs on forward and backward inference tasks. % Our demo system is available at https://github.com/dawonahn/ECML_PKDD_AnTenA. --- ### BV-Blend: Uncertainty-Weighted Historical Baselines for Stable Critic-Free RL with Verifiable Rewards Authors: Yupeng Chang, Yuan Wu, Yi Chang Published: 2026-06-27 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.28707v1 Critic-free reinforcement learning with verifiable rewards (RLVR), exemplified by Group Relative Policy Optimization (GRPO), avoids training a value function (critic) and reduces memory and compute overhead relative to critic-based PPO pipelines for aligning large language models. However, GRPO-style advantage estimation depends on prompt-local (within-prompt-group) reward statistics and can be unstable. In particular, when all rollouts in a prompt group receive identical rewards, the within-group reward variance becomes zero, and group normalization yields zero advantages for that group, impeding learning in cold-start regimes with binary verifiers. We introduce BV-Blend, a critic-free framework that stabilizes advantage estimation by combining prompt-local on-policy statistics with semantic-cluster-conditioned historical moments. BV-Blend maintains EMA-tracked reward moments for each cluster, derives a confidence weight from a standard error of the mean (SEM) proxy, and uses this weight to blend historical and prompt-local baseline and variance statistics into a standardized advantage for PPO-style clipped updates. Experiments on verifiable reasoning benchmarks show that BV-Blend improves training stability and performance, and remains robust in regimes where group-normalized methods may stall. --- ### Mitigating Batch Effects in Histopathology via Language-Mediated Robust Embedding Generation Authors: Yishu Zhang, Shushan Wu, Zhenzhong Zhang, Didong Li, Huaxiu Yao, Yun Li, Iain Carmichael, Katherine A. Hoadley, Hongtu Zhu, Di Wu, Daiwei Zhang Published: 2026-06-27 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2606.28697v1 Pathology foundation models (PFMs) have demonstrated strong potential across clinical and scientific applications, yet their performance is often hindered by batch effects, which are non-biological variations across tissue source institutions (TSIs) that distort learned feature representations and impair generalization. Conventional mitigation strategies, such as stain normalization, offer limited success in addressing these high-dimensional, complex artifacts. We present GLMP (General-purpose LLM-Mediated Pathology model), a novel framework that generates robust numerical embeddings from histology image patches through an intermediate textual representation. By leveraging pretrained general-purpose multimodal large language models (MLLMs) and text encoders, GLMP effectively prioritizes biologically meaningful signals over TSI-specific artifacts, thereby improving cross-institutional generalization. To our knowledge, GLMP is the first pathology model to use text descriptions of histological features as an intermediate representation for generating numerical embeddings from histology images. Our results highlight the untapped potential of broad-domain, non-specialized MLLMs in computational pathology and introduce a new paradigm for building versatile, generalizable, and robust pathology models. --- ### COMPASS: Grounding Composition-Intent Guidance in Unified Multimodal Models Authors: Ziqi Zhou, Weize Quan, Mining Tan, Zhihan Chen, Dandan Zheng, Jingdong Chen, Jun Zhou, Weiming Dong, Dong-Ming Yan Published: 2026-06-27 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.28696v2 Composition is a high-level visual intent that governs where subjects are placed and how a scene is organized, yet current unified multimodal models remain unreliable at fine-grained composition recognition and struggle to turn such intent into controllable generation. We present COMPASS, the first unified multimodal framework that grounds composition-intent control in a single system spanning both composition perception and composition-guided generation, with a shared expert token $τ_c$ as the central intent anchor. On the perception side, COMPASS injects composition expertise into an MoE backbone in a minimally invasive manner and distills the inferred intent into $τ_c$. On the generation side, COMPASS reuses $τ_c$ as a global conditioning signal that steers the denoising trajectory, effectively converting passive composition analysis into explicit layout control. To support systematic instruction-following composition learning and evaluation at scale, we construct Comp-11, a large-scale dataset with an 11-class taxonomy and reasoning-augmented annotations. Extensive experiments show that COMPASS substantially improves category-level composition understanding and delivers more composition-consistent, prompt-faithful generation than strong baselines. --- ### COMPASS: Grounding Composition-Intent Guidance in Unified Multimodal Models Authors: Ziqi Zhou, Weize Quan, Mining Tan, Zhihan Chen, Dandan Zheng, Jingdong Chen, Jun Zhou, Weiming Dong, Dong-Ming Yan Published: 2026-06-27 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.28696v1 Composition is a high-level visual intent that governs where subjects are placed and how a scene is organized, yet current unified multimodal models remain unreliable at fine-grained composition recognition and struggle to turn such intent into controllable generation. We present COMPASS, the first unified multimodal framework that grounds composition-intent control in a single system spanning both composition perception and composition-guided generation, with a shared expert token $τ_c$ as the central intent anchor. On the perception side, COMPASS injects composition expertise into an MoE backbone in a minimally invasive manner and distills the inferred intent into $τ_c$. On the generation side, COMPASS reuses $τ_c$ as a global conditioning signal that steers the denoising trajectory, effectively converting passive composition analysis into explicit layout control. To support systematic instruction-following composition learning and evaluation at scale, we construct Comp-11, a large-scale dataset with an 11-class taxonomy and reasoning-augmented annotations. Extensive experiments show that COMPASS substantially improves category-level composition understanding and delivers more composition-consistent, prompt-faithful generation than strong baselines. --- ### An AI agent for treatment reasoning over a biomedical tool universe Authors: Shanghua Gao, Ayush Noori, Richard Zhu, Curtis Ginder, Zhenglun Kong, Xiaorui Su, Justin Kauffman, Benjamin S. Glicksberg, Joshua Lampert, Ankit Sakhuja, Ashwin Sawant, ATHENA-R1 Evaluation Consortium et al. Published: 2026-06-27 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.28692v1 Treatment reasoning underpins every therapeutic decision, integrating disease context, comorbidities, medications, contraindications, and evolving biomedical knowledge to select an appropriate therapy. It is inherently iterative: candidates are weighed against many constraints, revised as evidence emerges, and grounded in verifiable sources. Here we introduce ATHENA-R1, an AI agent for treatment reasoning across all FDA approved drugs since 1939, trained by reinforcement learning over a universe of 212 biomedical tools. At each step it identifies missing information, selects and runs relevant tools, and incorporates the evidence. To train it without human-annotated traces, we build a two-level self-learning framework: multi-agent systems construct the tools, tasks, and reasoning trajectories for supervised fine-tuning, then reinforcement learning with scientific feedback rewards reasoning quality (evidence gathering, grounded tool use, logical non-redundancy). Across five benchmarks of 3,168 drug reasoning tasks and 456 patient treatment cases, ATHENA-R1 outperforms language models and tool-use systems, reaching 94.7% accuracy on open-ended drug reasoning and 82.9% on treatment reasoning, 17.8 and 10.7 points above GPT-5. In blinded evaluations by experts from 28 rare disease organizations, it is preferred over reference models on all criteria, and physicians rated it favorably on complex hospitalized cardiovascular and infectious-disease cases. Adverse-event hypotheses it generated, tested in electronic health records from 5.4 million patients, reached adjusted odds ratios of 1.48-1.84, with no elevation among negative controls. Because it requires knowing what evidence to seek before concluding, treatment reasoning has long been hard for AI; we show it can be reframed as a learnable process of iterative evidence gathering that reinforcement learning can train AI to perform. --- ### LogiCo: A Unified Framework for Logical and Structural Anomaly Detection Authors: Ximiao Zhang, Min Xu, Xiuzhuang Zhou Published: 2026-06-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.28688v1 Current anomaly detection methods primarily focus on structural anomalies, while paying insufficient attention to anomalies that violate logical constraints. Conversely, top-performing logical anomaly detection approaches address this by modeling global semantic consistency, but perform poorly on subtle structural anomalies due to inadequate detection granularity. In this paper, we propose LogiCo, a unified framework for Logical and structural anomaly detection via Component-level feature reconstruction. Unlike existing methods that rely on explicit global semantic modeling, LogiCo employs a novel component-level feature reconstruction technique to capture inter-component logical constraints. Specifically, LogiCo maps pre-trained image features into a discrete component-level feature space and performs collaborative feature reconstruction at both component and patch levels, enabling it to effectively detect both logical and structural anomalies. Furthermore, to address the specific challenge of count-related logical anomalies, we integrate a segmentation-map discriminator that extends the model's capability to identify quantitative inconsistencies. LogiCo achieves state-of-the-art performance on both logical and structural anomaly detection across four benchmarks, including MVTec-LOCO, MVTec-AD, VisA, and Real-IAD, demonstrating its superiority and practical feasibility. The code is available at https://github.com/cnulab/LogiCo. --- ### A Neuroimaging Simulation Framework for Developing and Evaluating Causal AI Authors: Eryn Libert-Scott, Emma A. M. Stanley, Vibujithan Vigneshwaran, Matthias Wilms, Erik Y. Ohara, Nils D. Forkert Published: 2026-06-27 Categories: eess.IV, cs.LG arXiv: https://arxiv.org/abs/2606.28684v1 Causally linking disease-related factors to image-derived biomarkers provides a powerful pathway to understanding disease mechanisms. Despite growing interest in applying causal artificial intelligence (AI) approaches for this task, these methods still need to be adapted for complex medical images, and especially, neuroimaging. However, the lack of ground-truth data presents a barrier to development. To bridge this gap, we developed and tested a method for generating synthetic neuroimages, which adhere to a user-specified causal structure describing the non-image to image variable relationships, permitting the creation of ground-truth neuroimaging datasets. In the simulated T1-weighted magnetic resonance images, anatomical variability is modeled by sampling from a subspace estimated from real data and deforming a template image to create unique simulated subjects. Causal relationships are encoded via precise volumetric changes of any region-of-interest without unwanted global artifacts. We achieved relative volume errors of 0.3-2.66% for the targeted regions-of-interest and demonstrate their statistically significant causal relationships, while maintaining mean absolute errors for non-target brain regions between 0.034-0.397ml. An initial evaluation of causal discovery methods exposes their limited ability to suppress spurious connections, highlighting the need for image-appropriate methods. Our framework is the first to enable the generation of realistic synthetic 3D neuroimages with explicit causal control that can serve as the missing ground-truth data necessary for the objective benchmarking and development of causal AI methods. --- ### Aristotelian Virtue Profiling of LLMs through Ethical Dilemmas Authors: Ioannis Tzachristas, John Pavlopoulos Published: 2026-06-27 Categories: cs.AI, cs.CY, stat.AP, stat.ME arXiv: https://arxiv.org/abs/2606.28683v1 Large Language Models (LLMs) often face ethical tradeoffs in which several responses may be defensible but express different priorities, such as fairness, honesty, courage, or restraint. We introduce VirtueMap, a framework for describing these patterns through an Aristotelian virtue-ethics lens. Instead of asking for a single correct answer, VirtueMap asks humans or LLMs to rank all five responses to each of seven general, non-lethal, non-political, and non-religious ethical dilemmas. To define the reference orderings used for scoring, we first proposed, for each dilemma and virtue, an ordering of the five responses from most to least expressive of that virtue. We then collected more than 100 respondent evaluations per ordering and retained it as operational ground truth only when at least 95% confirmed it. Rankings are scored against these retained orderings using normalized Borda alignment, yielding profiles over Practical Wisdom, Justice, Truthfulness, Courage, and Temperance. We apply VirtueMap to nine LLM families in a repeated-run evaluation and find high mean rank consistency (90.3%), with the largest differences appearing on Courage, Temperance, and Justice. We also release an interactive website that computes profiles locally in the browser and compares respondents with measured LLM profiles. --- ### Capability Gates Are Not Authorization: Confused-Deputy Failures in LLM Agent Frameworks Authors: David Mellafe Zuvic Published: 2026-06-27 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2606.28679v1 Tool-using LLM agents increasingly read untrusted content while holding side-effecting tools such as payments, email, CRM, and infrastructure APIs, yet common framework defaults still conflate tool exposure with authorization. We audit whether LangChain/LangGraph, LlamaIndex, and the Stripe Agent Toolkit re-authorize each model-emitted call, with concrete argument values, before execution. Across pinned public-source commits, all three provide capability gating by default, but none provides a deterministic fail-closed per-call value authorization gate by default. We introduce ScopeGate, a five-stage PDP/PEP for agent tool calls: scope, authorization, money ceiling, idempotency, and default deny. Evaluation shows the identical unauthorized payout call executes under LangChain's default dispatch (with a companion LlamaIndex PoC) but is denied by ScopeGate; the tested control reports 0/48 static bypasses, 0/29 unauthorized attempts (40-iteration adaptive run), 0/10 benign false-denies, and Latam-GPT payment-agent containment at 10/10. ASR denotes attempted unauthorized action, containment is not a cure, deployment-tier claims are inference over measured model classes, and no CVE is asserted. --- ### SATB-VR: Training Few-Step Video Restoration Diffusion Model using SNR-Aware Trajectory Blending Authors: Haoran Bai, Xiaoxu Chen, Xiaoyu Liu, Zongsheng Yue, Sibin Deng, Wangmeng Zuo, Ying Chen Published: 2026-06-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.28677v1 While diffusion models excel in video restoration, their reliance on extensive iterative steps limits efficiency. Conversely, aggressive single-step distillation often compromises fine texture recovery. To achieve an optimal balance, we present SATB-VR, a few-step paradigm that jump-starts the denoising process via an auxiliary predictor, explicitly bypassing early low signal-to-noise ratio (SNR) steps. However, naive joint training of the predictor and the denoiser inherently introduces a severe train-inference discrepancy. To resolve this, we propose the SNR-Aware Trajectory Blending (SATB) strategy. During the forward process, SATB constructs the noisy input by dynamically blending the predictor's output with the ground-truth trajectory based on the SNRs. This forces the denoiser to robustly compensate for initial prediction errors while smoothly converging to the clean data manifold. Furthermore, we introduce a Denoiser-Driven Consistency (DDC) loss, leveraging the concurrently updated denoiser as a dynamic evaluator to explicitly align internal features and boost predictor accuracy. Extensive experiments demonstrate that, under flexible few-step inference regimes (\eg, $\le 5$ steps), SATB-VR performs favorably against existing approaches on synthetic, real-world, and AIGC benchmarks. --- ### Predicting Metastatic Risk from Primary Cancer Tissue Architecture via Distance-Aware Spatial Modeling Authors: Sandesh Pokhrel, Hamid Manoochehri, Beatrice S Knudsen, Tolga Tasdizen Published: 2026-06-27 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.28676v2 Predicting distant metastasis from the digital H & E slides of the primary tumor is a critical yet challenging task in computational pathology. Multiple Instance Learning (MIL) approaches can attend to subdomains in whole slide images (WSIs) that harbor features of pre-metastatic cancer regions. However, conventional MIL models largely treat tissue patches as unordered bags, discarding the spatial layout that defines how these regions are arranged and interact across the tissue. We propose that metastatic risk is shaped not only by local patch appearance, but also by the geometric organization of patches in the WSI and the interaction between the tissue compartments. To this end, we introduce Distance-aware Tissue Modeling for Multiple Instance Learning (DTMF-MIL), a spatial MIL framework that reinforces feature embeddings with explicit distance priors. By computing signed distance functions (SDFs) to capture regions with similar features, and representing each patch with radial-basis distance responses and local SDF statistics, DTMF-MIL learns positions of patches with respect to regional interiors and boundaries. The interactions between similar patches are contextualized across local tissue neighborhoods and used to guide slide-level attention while pooling patch feature evidence for metastasis prediction. We evaluate DTMF-MIL for prediction of distant prostate cancer metastasis in an internal prostate needle-biopsy cohort (IPC) from a large hospital system and on public TCGA-COAD and TCGA-KIRC datasets across multiple pathology foundation-model backbones. Across most dataset, backbone, and metric combinations, DTMF-MIL achieves the strongest results consistently. --- ### Predicting Metastatic Risk from Primary Tissue Architecture via Distance-Aware Spatial Modeling Authors: Sandesh Pokhrel, Hamid Manoochehri, Bodong Zhang, Beatrice S Knudsen, Tolga Tasdizen Published: 2026-06-27 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.28676v1 Predicting the risk of distant metastasis from primary tumor tissue histology is a critical yet challenging task in computational pathology. Multiple Instance Learning (MIL) approaches can attend to subdomains in tumor regions that harbor features of metastatic cancer progression. However MIL models treat tissue patches as unordered bags, discarding the spatial layout that defines the metastatic potential. We propose that metastatic risk is inherently dictated by the geometric arrangement of the tumor microenvironment at the interface with tumor cells. Our model is designed to explicitly capture the spatial relationships between tumor cells, tumor associated fibroblasts and infiltrating lymphocytes. For this purpose, we propose Distance aware Tissue Modeling for Multiple Instance Learning(DTMf-MIL), a novel method that reinforces visual features with explicit spatial priors. By computing signed distance functions (SDF) relative to tissue phenotypes, our model learns to recognize structural signatures of metastatic risk. This geometric awareness translates directly to superior clinical performance as DTMf-MIL significantly outperforms state-of-the-art methods that ignore spatial layout on metastasis prediction from tissue in the primary tumor. We further validate our approach on public benchmarks, demonstrating that spatial awareness consistently improves diagnostic accuracy across diverse clinical tasks. --- ### Constrained Tabular Diffusion for Finance Authors: Michael Cardei, Jose M Munoz, Oscar Barrera, Shreyas K Chandrahas, Partha Saha Published: 2026-06-27 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.28674v1 Generative models in finance face the dual challenge of producing realistic data while satisfying strict regulatory and economic objectives, a requirement that standard tabular diffusion models cannot provide. To address this difficulty, we introduce Constrained Tabular Diffusion for Finance (CTDF), a novel integration of sampling-time feasibility operations with mixed-type tabular diffusion in financial applications. By incorporating a training-free feasibility operator into the reverse-diffusion sampling loop, CTDF enforces hard constraints for applications such as simulation, legal compliance, and extrapolation. Extensive experiments on large-scale financial datasets demonstrate zero constraint violations and improvement in scarce data utility. CTDF establishes a robust method for generating trustworthy and compliant synthetic data, opening new avenues for rigorous generative modeling and analysis in the financial domain. --- ### BackTranslation2.0 -- A Linguistically Motivated Metric to Assess Sign Language Production Authors: Oliver Cory, Maksym Ivashechkin, Karahan Sahin, Oline Ranum, Jianhe Low, Edward Fish, Anton Pelykh, Ozge Mercanoglu Sincan, Richard Bowden Published: 2026-06-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.28673v1 Sign Languages (SLs) are the primary means of communication for millions of deaf individuals, yet existing evaluation metrics for generated SL remain simplistic and poorly aligned with human judgements. We introduce BackTranslation2.0, a linguistically grounded evaluation metric for text-to-sign translation that moves beyond naïve backtranslation. Our approach adopts an agentic framework in which a deterministic pipeline orchestrates a suite of specialised tools to assess four scoring dimensions - grammatical correctness, phonological accuracy, motion fluency, and generation fidelity - aligned with human rater assessments. Tool outputs are not treated independently: a set of large language model (LLM)-based cross-referential comparison modules evaluates consistency across tools and checks outputs against linguistic expectations, enabling structured reasoning over grammatical, phonological, and motion-level evidence. Final dimension scores are computed through deterministic weighted formulas over validated tool outputs. To validate BackTranslation2.0, we introduce and evaluate on a British Sign Language (BSL) dataset rated in a human rater study across the same quality dimensions, following a protocol developed in collaboration between linguists and deaf experts, benchmarking against six baseline metrics. Our method demonstrates strong correlation with human judgements across all dimensions, providing a more comprehensive, interpretable, and linguistically principled evaluation framework for sign language production systems. --- ### Entropy-Regularized Reinforcement Learning for Linear-Quadratic Stackelberg Differential Games in Regime-Switching Diffusion Models Authors: Congde Hu, Danping Li, Lin Xu, Wenying Xu Published: 2026-06-27 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.28671v1 Stackelberg differential games (SDGs) provide a powerful framework for hierarchical decision-making in stochastic and continuous-time environments, yet their solution remains computationally challenging due to the complexity of traditional dynamic programming and Hamilton-Jacobi-Bellman-Isaacs (HJBI) methods, especially in high-dimensional systems. This paper proposes an entropy-regularized reinforcement learning (ERRL) approach for linear-quadratic SDGs (LQ-SDGs) within a continuous-time diffusion framework governed by Markovian regime switching. The key innovation lies in deriving exploratory weakly-coupled HJBI equations with entropy regularization, which promotes stochastic policies that actively avoid suboptimal equilibria -- a limitation of classical SDG methods. Neural networks are integrated to approximate regime-dependent value functions and solve high-dimensional partial differential equations (PDEs) efficiently, while a novel sampling technique enhances computational tractability. Numerical results demonstrate the effectiveness of the framework compared to conventional approaches, particularly in escaping suboptimal traps through exploratory policies. The study highlights the critical role of entropy regularization and neural network approximations in achieving robust solutions for hierarchical decision-making problems under abrupt environmental shifts. --- ### MACROCAST: A Vintage-Consistent Time Series Foundation Model for Real-Time Macroeconomic Forecasting Authors: Andrea Carriero, Davide Pettenuzzo, Shubhranshu Shekhar Published: 2026-06-27 Categories: econ.EM, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.28670v1 We introduce MACROCAST, a lightweight Time Series Foundation Model (TSFM) for real-time macroeconomic forecasting. Existing TSFMs suffer from data leakage in two forms: temporal contamination, as the model may have seen the realized values of the series it forecasts, and revision bias, as training on fully revised data diverges from the preliminary, vintage-specific releases available to real-time forecasters. MACROCAST is, to our knowledge, the first TSFM that rules out both forms of leakage entirely: at no stage of training is the model exposed to information that would not have been available to a forecaster in real time. We train MACROCAST first on purely synthetic time series in approximately one GPU-day and then fine-tune it on synthetic time series drawn from Bayesian VARs, dynamic factor models, and ARIMA specifications estimated on vintage-specific ALFRED data. Because pretraining uses only simulated data and fine-tuning uses only real-time vintages, no observed future or revised value ever enters the model; each fine-tuning run takes nine minutes. Evaluated on the FRED-MD database in a genuine real-time out-of-sample exercise, MACROCAST improves on the AR(1) benchmark for roughly 80% of series-horizon pairs, matches or surpasses Chronos-2 -- the strongest currently available TSFM -- and outperforms the Bayesian VAR and dynamic factor model benchmarks, all in a data-leakage-free manner. --- ### Entropy Regularized Reinforcement Learning for Zero-Sum Stochastic Differential Games in a Regime-Switching Jump-Diffusion Process Authors: Congde Hu, Zhuo Jin, Danping Li, Lin Xu Published: 2026-06-27 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.28669v1 To address parameter misspecification and sudden structural environmental changes in conventional stochastic differential game (SDG) frameworks, this paper introduces a distributional control approach that characterizes optimal strategies as probability distributions over actions, conditioned on the continuous state, the discrete regime state, and parameters. This forms a reinforcement learning framework for entropy-regularized zero-sum stochastic differential games (ERRL-ZSSDGs) in a regime-switching jump-diffusion process. Using the dynamic programming principle (DPP), we derive the associated coupled systems of Hamilton-Jacobi-Bellman-Isaacs (HJBI) equations, from which equilibrium strategies are expressed via gradients of the value function. For linear-quadratic problems, semi-analytical solutions for both value function and equilibrium strategies are obtained by solving a system of coupled ordinary differential equations (ODEs). In more general settings, an Actor-Critic policy improvement algorithm is developed to approximate the value functions and equilibrium policies across different regimes. The method is applied to an investment game, and numerical examples illustrate the effect of the temperature parameter and regime transitions on optimal policies and values. --- ### Phonological Perception of Sign Language Models Authors: Kayo Yin, Jessica Carter, Alex Xijie Lu, Annemarie Kocab Published: 2026-06-27 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.28667v1 Sign languages are compositional systems where meaning arises by combining sublexical phonological parameters, such as handshape, location, and movement. While deep learning models for Sign Language Recognition (SLR) have achieved increased performance on translation benchmarks, it remains unclear whether these models distinguish abstract phonological features or merely rely on low-level statistical correlations. This work evaluates the phonological perception of SLR models trained on American Sign Language (ASL) by probing phonological sensitivity using minimal pairs and evaluating representational alignment with human behavioral data. Our results reveal that SLR models exhibit emergent phonological sensitivity, but with clear architectural trade-offs: pose-based models are sensitive to handshape contrasts, while pixel-based models better capture location changes. Furthermore, pose-based models learn latent representations that correlate with human perceptual similarity judgments (r~0.49). These findings suggest that while SLR models exhibit emergent phonology, current training paradigms are insufficient to scale them beyond their architectural inductive biases. --- ### Why Trust Your Agent? Empirical Security Gains from TRiSM-Guided Agentic Workflows in Healthcare Authors: Liam Kearns Published: 2026-06-27 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2606.28666v1 Agent-based AI has enabled the automation of tasks by exposing application tools and resources to large language models (LLMs). However, to improve scope and accuracy, agents are often given access rights that exceed those of ordinary users, introducing significant security risks. AI is routinely integrated into applications with a disregard to security, risking data exposure and breaching regulations. This paper applies the AI Trust, Risk, and Security Management (TRiSM) framework to a medical report-generation application to demonstrate how an insecure agent workflow can be transformed into security-conscious agentic workflow. Both workflows were evaluated across five LLMs (Claude Haiku 4.5, GPT-4.1-nano, GPT-4.1-mini, GPT-5.4-mini, and Gemini 2.5 Flash) on two report types, totalling 800 generations and 500 attack scenarios including RAG poisoning, data-field injection, and client-side network injection. The TRiSM-guided agentic workflow reduced mean attack success rates from 31% to 10% for RAG poisoning and from 42% to 25% for data-field injection, while eliminating the network injection vector entirely through server-side prompt construction. Furthermore, report accuracy increased by 14 percentage points (72.5% to 86.5%) with the agentic workflow, demonstrating a secure design which provides more reliable outputs. This paper contributes to knowledge by demonstrating least-privilege, defence in depth agentic workflows improving security and accuracy, while also highlighting model choice is a necessary architectural consideration. --- ### Closed-Form Steepest Descent Direction toward Flat Minima: Reducing Upper Bounds on the Loss Hessian Eigenspectrum in Neural Networks Authors: Yuto Omae, Kazuki Sakai, Yohei Kakimoto, Makoto Sasaki, Yusuke Sakai, Hirotaka Takahashi Published: 2026-06-27 Categories: cs.LG, cs.AI, cs.NE arXiv: https://arxiv.org/abs/2606.28662v1 The flatness hypothesis suggests that flatness of the loss landscape, as measured by the eigenvalues of the loss Hessian, correlates with better neural network generalization. While various algorithms reduce these eigenvalues, most focus on procedural design, leaving it unclear how data distributions and NN parameters structurally determine directions toward flat minima. Characterizing these directions analytically is generally intractable. To overcome this mathematical difficulty, recent studies derived the Wolkowicz-Styan (WS) upper bound on the maximum eigenvalue of the cross-entropy loss Hessian in three-layer NNs. Although this upper bound is differentiable, its gradient was not derived. Therefore, we analytically derive the gradient of the WS upper bound to characterize directions leading to flat minima. Based on this, we propose Hessian Spectral Range (HSR) Regularization, which updates parameters along the steepest descent direction of the WS bound. Experiments demonstrate that HSR Regularization narrows the Hessian eigenvalue spectrum, avoids sharp minima and saddle points, and promotes convergence to flat minima. Although the applicability of this method is currently limited to cross-entropy loss and three-layer architectures, to the best of the authors' knowledge, this is the first study to report a closed-form gradient that promotes convergence to flat minima without numerical approximations. Therefore, the theoretical analysis of this gradient is expected to contribute to the further development of NNs. --- ### When More Sampling Hurts: The Modal Ceiling and Correlation Ceiling of Test-Time Scaling Authors: Yong Yi Bay, Kathleen A. Yearick Published: 2026-06-27 Categories: cs.LG, cs.AI, cs.CL, stat.ML arXiv: https://arxiv.org/abs/2606.28661v1 People overthink; language models over-sample, and the extra effort can talk both into a worse answer. Reasoning systems answer a hard question by sampling it many times (test-time scaling), and the more they draw, the more often a correct answer turns up somewhere, so coverage, the fraction of problems with at least one correct try, climbs and appears to be progress. But a deployed system must return one answer, and choosing it, not knowing which try is right, is selection; selection is capped, and past a point extra samples only make the model surer of a confident mistake, even as every draw adds cost. The gap between climbing coverage and stalled selection, the identifiability gap, is the answer a model can produce but not pick. So the real question is not whether to sample but how far, and the answer is: not far. For picking an answer, the vote has already settled within a few dozen draws, the modal ceiling; for scoring a benchmark, sooner still, the correlation ceiling. Beyond that, extra draws cost compute and add nothing, and can even make the answer worse. This paper turns the cutoff into a single number, the effective number of samples, that any sampling run already reveals. The bottleneck is recognizing a right answer, not generating one. --- ### Transformer-Based Active Learning for Data-Efficient Vaccine Epitope Selection in PRRS Authors: Aspen Erlandsson Brisebois, Zahed Khatooni, Connor Burbridge, Brook Byrns, Heather L. Wilson, Sureesh Tikoo, Steven Rayan, Gordon Broderick Published: 2026-06-27 Categories: q-bio.BM, cs.LG arXiv: https://arxiv.org/abs/2606.28659v1 High-fidelity molecular docking simulations can produce biologically relevant estimates of epitope-receptor binding affinity but are computationally expensive and therefore limit the number of candidates that can be screened for vaccine design. In this work, we evaluate machine learning (ML) approaches where variants of active learning are used to classify instances of high binding affinity between 9-mer epitopes and a well-conserved swine leukocyte antigen (SLA) receptor in the context of Porcine Reproductive and Respiratory Syndrome (PRRS). We use an internally generated dataset of 80 epitope-SLA docking affinities, each requiring more than 48 hours of high-performance computing (HPC). Multiple model families (linear, MLP, CNN, and a small transformer) are trained under strict low-data conditions within a pool-based active learning loop. In each case, optimal model configurations are identified by conducting large-scale hyperparameter optimization over the combined space of model architecture, training configuration, acquisition policy, and ensemble decision rules. To mitigate the effects of data subsample selection, each candidate configuration is evaluated by averaging performance over many randomized and balanced training and validation data subsets. Across experiments, transformer-based sequence models consistently emerged as the best-performing architecture, with active incremental learning yielding significant improvement over a baseline random sample acquisition strategy. Under moderate training data availability (N=30), the optimized ML-model configuration outperforms a standard baseline trained on twice the amount of data. Under higher training data availability (N=60), the same configuration achieves a peak accuracy of 86.8%, consistent with an upper bound of 85% classification accuracy based on two independent estimates of conformational noise. --- ### SemDynReg: Semantics-Guided Deformation Regularization for Dynamic 3D Gaussian Splatting Authors: Ruitao Chen, Mozhang Guo, Jinge Li Published: 2026-06-27 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.28656v1 Deformable 3D Gaussian Splatting (3DGS) has emerged as an efficient approach for rendering dynamic scenes in a wide range of 3D applications. However, existing deformation field-based approaches largely lack explicit object-level modeling, often resulting in inconsistent Gaussian deformations within individual objects and unwanted coupling between different objects. To address this limitation, we introduce a semantics-guided framework that enforces dynamic regularization at the object level, aiming to achieve spatially consistent object-wise deformation. Specifically, we first extract segmentation masks using the Segment Anything Model (SAM) and derive semantic features from input images. An object-ID map is then constructed via feature relevance matching with a predefined object dictionary. Guided by this object-ID map, we identify the pixel-wise top-k contributing Gaussians for each object and impose consistency regularization on their deformation parameters, including position, scale, and rotation. Unlike prior methods that learn deformation fields without explicit object-level constraints, our approach incorporates semantic cues to guide deformation behavior at the object level. Experimental results demonstrate that our semantics-aware regularization improves object-level deformation consistency and outperforms baseline methods in rendering quality, achieving higher PSNR and SSIM and lower LPIPS in dynamic 3DGS rendering. Our project page is available at https://dyn-reg-3dgs.github.io/. --- ### Exploring the Effects of Entanglement on Quantum Machine Learning of Pathogen Epitope-Receptor Binding Authors: Aspen Erlandsson Brisebois, Luis Pablo Gonzalez Dominguez, Shivansi Prajapati, Zahed Khatooni, Heather L. Wilson, Connor Burbridge, Brook Byrns, Sureesh Tikoo, Christophe Pere, Steven Rayan, Gordon Broderick Published: 2026-06-27 Categories: quant-ph, cs.LG, q-bio.BM arXiv: https://arxiv.org/abs/2606.28655v1 Parameterized quantum circuits (PQCs) provide a flexible substrate for hybrid quantum machine learning (QML), but their practical value on Noisy Intermediate-Scale Quantum (NISQ) devices remains an empirical question, especially because training depth and scale can introduce optimization challenges such as barren plateaus. Here we study how the number and topology of two-qubit entangling gates in the feature-map stage influence a fixed hybrid QNN workflow for classifying strong versus weak epitope-receptor binding in Porcine Reproductive and Respiratory Syndrome (PRRS) vaccine design. The dataset consists of docking-derived binding affinities for N=80 9-mer epitopes, labeled as Strong or Weak binding, and partitioned into training, validation, and test subsets using a 40:30:30 split. We compare a classical CNN benchmark with a hybrid Embedding-QNN architecture under four feature-map configurations: a non-entangling Z feature map, an all-to-all high-entanglement ZZ feature map, and two interleaved nearest-neighbour entanglement patterns of low and high depth. Among the configurations tested, the high-entanglement ZZ feature map is seen to provide the strongest evidence of reduced training-set overfit, with a lower training area under the accuracy curve (AUAC) and the highest test/training AUAC ratio, while preserving competitive test-set accuracy. These results do not establish a general QML advantage, but they suggest that feature-map entanglement topology is a meaningful design variable for sparse biological screening tasks and warrants further evaluation with additional metrics, larger datasets, and noise-aware or hardware-based experiments. --- ### Physics-Informed Conformal Prediction: Embedding PDE Consistency into Distribution-Free Uncertainty Quantification for Neural Operators Authors: Michael Chin Published: 2026-06-26 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.11935v1 Neural operators such as the Fourier Neural Operator (FNO) achieve remarkable accuracy in approximating solutions to partial differential equations (PDEs). However, providing rigorous uncertainty estimates remains an open challenge. We propose Physics-Informed Conformal Prediction (PI-CP), a framework that embeds PDE residuals into the nonconformity score of split conformal prediction, producing prediction intervals that are (i) distribution-free with provable coverage guarantees, and (ii) spatially adaptive when the PDE residual correlates with prediction error -- tighter where physics is well-satisfied, wider where it is violated. Additionally, we prove that FNO's translation equivariance creates a fundamental approximation barrier for PDEs with Dirichlet boundary conditions, and show that coordinate channels resolve this with up to 63x error reduction. We validate PI-CP across six physics scenarios -- heat conduction (2D/3D), structural mechanics (2D/3D), Darcy flow, and Navier-Stokes -- demonstrating consistent 89-91% coverage for all four Conformal methods, while MC Dropout and Deep Ensembles are unstable (82-100%). FNO outperforms CNN and DeepONet by 10-12x. --- ### Position Is All You Need: A Free Lunch Token Compression Strategy for MLLM-based Referring Expression Segmentation Authors: Yuhan Liu, Yixiong Zou, Yuhua Li, Ruixuan Li Published: 2026-06-26 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.26142v1 Referring Expression Segmentation (RES) aims to generate pixel-wise segmentation masks from complex and implicit textual queries. While recent advances in Multimodal Large Language Models (MLLMs) have substantially boosted RES performance, their prohibitive computational overhead remains a critical bottleneck, which, however, is rarely explored. To fill this gap, we first evaluate typical token compression methods on this task and observe a surprising performance degradation. In this paper, we aim to understand this phenomenon for a solution. By extensive experiments, we find that token compression for RES requires preserving the original position embeddings and local neighboring spatial structures, indicating that visual token position information is far more critical than in other tasks. Building on this insight, we ask: Can we design the token compression method purely based on the position information? Therefore, we propose PAYN, a plug-and-play, training-free token compression method that relies solely on position information. PAYN retains tokens that are adequately distributed in every local neighboring region while strictly preserving original positional indices, thereby maintaining spatial relational consistency. Experiments on multiple RES benchmarks demonstrate that our method outperforms existing token compression methods, verifying that position is indeed all you need for token compression in the MLLM-based RES task. Codes are avaliable at https://github.com/YuhanLiu231/PAYN. --- ### AdaThinking-E: One-Token Entropy Regulation for Adaptive Thinking Authors: Zining Wang, Tongkun Guan, Boming Chen, Zhentao Guo, Jianqiang Liu, Chao Jin, Chen Duan, Kai Zhou, Pengfei Yan, Wei Shen, Xiaokang Yang Published: 2026-06-26 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2608.26141v1 Multimodal large language models have demonstrated strong document reasoning capabilities by incorporating explicit thinking processes. While this capability significantly improves performance on challenging tasks, current models apply such deep reasoning uniformly to all questions, resulting in unnecessary computational overhead for simple task. This not only degrades user experience but also negatively impact accuracy on benchmark datasets. We identify the critical need for adaptive thinking mechanisms that can intelligently determine when to engage reasoning based on question complexity. To address this, we propose AdaThinking-E, a novel reinforcement learning framework that learns adaptive thinking through one-token entropy regulation. Our key insight is that model confidence in the decision to engage thinking (or not) can be quantified through entropy analysis of the predicted probability distribution at critical decision tokens. This observation motivates our entropy-governed reward mechanism: the training process naturally transitions from high-entropy exploration, where the model experiments with different thinking strategies, to low-entropy convergence with confident, generalizable decision-making policies. Crucially, this approach enables models to intrinsically discover when to think without requiring manual intervention or external difficulty labels. Extensive experiments demonstrate that our approach enables models to be both accurate on complex problems and efficient on simple ones across diverse document tasks. --- ### Affix Cache for Diffusion Large Language Models Authors: Kaihua Liang, An Zhong, Xin Tan, Zafar Ayyub Qazi, Hong Xu, Jian Weng, Marco Canini Published: 2026-06-26 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2608.26140v2 Diffusion Large Language Models (DLLMs) enable non-autoregressive decoding, but efficient inference support remains immature: unlike autoregressive models, whose requests reuse a shared prefix key-value (KV) cache, DLLMs use bidirectional attention, so a shared context's KV states depend on the tokens still being decoded, leaving directly reused caches stale and full recomputation necessary. We present ACache, a cross-request cache reuse mechanism for shared spans, or affixes, at any position: prefix, infix, or suffix. ACache measures the influence of affix tokens on the masked generation region to identify a small request-specific subset as Anchor Tokens, and recomputes only their KV states while reusing the remaining affix cache. Built on state-of-the-art intra-request caching mechanisms, ACache recovers most of the accuracy lost to direct affix-cache reuse on average when recomputing around 20% of affix tokens, and at that budget preserves more accuracy than selection criteria adapted from prior cross-request cache-reuse systems. We co-design ACache with a modern inference engine, whose attention reads each request's recomputed Anchor KV states alongside one affix cache shared across concurrent requests. Against the same system with only intra-request caching, ACache cuts recompute latency by up to 56.7%, translating to as much as 1.71$\times$ end-to-end throughput, while reducing peak KV cache memory by up to 45.8%. --- ### Syntax vs. Semantics: How Transformers Learn Deep Dependencies Authors: Jiangrui Zhao, Xiaoting Du Published: 2026-06-26 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.26139v1 Large Language Models demonstrate remarkable syntactic fluency, yet the optimization dynamics governing their acquisition of deep semantic dependencies remain poorly understood. We propose a mechanistic framework that models this learning process as a competition between Surface Statistics and Deep Semantics. Our theoretical analysis identifies a ``Gradient Starvation" phenomenon where the error signals for sparse semantic dependencies are actively suppressed during early optimization. This suppression impedes the learning of structural reasoning and causes its emergence to manifest as a sudden phase transition. Furthermore, this framework offers a mechanistic basis for the effectiveness of Chain-of-Thought (CoT) strategies. By externalizing intermediate reasoning steps into concrete tokens, CoT effectively bypasses the suppression regime inherent to implicit reasoning. We validate these findings across scales ranging from toy transformers to production models (Llama-3.1-8B, Qwen2.5-Coder-7B). Finally, guided by this theory, we propose a topology-aligned contrastive objective that explicitly rectifies the gradient geometry. Experiments on variable binding tasks demonstrate that our method achieves an improvement that is over 2x larger than that obtained via standard cross-entropy fine-tuning. --- ### A Human-Factors Guided Cognitive Model of Visuospatial Complexity in Embodied Active Vision Authors: Vasiliki Kondyli, Jakob Suchan, Mehul Bhatt Published: 2026-06-26 Categories: q-bio.NC, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2608.23572v1 We propose a novel framework for the analysis of multimodal data -- encompassing visual, auditory, and spatial stimuli -- foregrounding the role of complexity in embodied perception and interaction in dynamic, naturalistic settings. Grounded in theories of embodied cognition and active vision, we argue that embodied perceptual complexity emerges from an agent's dynamic engagement with the environment and must be analyzed holistically, as a combination of qualitative and quantitative attributes pertaining to, for instance, visuospatial and auditory features. Building on previous work on visual complexity, we expand this into a categorization of diverse complexity attributes -- quantitative, structural, dynamic, auditory, and interactional -- that together characterize multimodal complexity. We demonstrate how this model provides a theoretical framework for characterizing aspects of visuospatial complexity and their interactions, specifically in the context of everyday driving. We also discuss practical applications of the proposed model for creating and evaluating benchmark datasets (e.g., in driving) that centralize cognitive human factors, as well as applications aimed at systematically investigating the effect of visuospatial complexity on human active vision from the viewpoint of visual perception research. The proposed framework lays the foundation for automated methods that interpret complexity in 3D dynamic environments from a human-centered perspective, serving as a semantic template for explainable computational analysis of visuospatial complexity with a categorical focus on cognitive human factors. --- ### AI Learning and Conceptual Transfer in the Game of Hidden Rules Authors: Christo Mathew, Wentian Wang, Jacob Feldman, Lazaros K. Gallos, Paul B. Kantor, Vladimir Menkov, Hao Wang Published: 2026-06-26 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.21372v1 This report summarizes the work conducted on the Game of Hidden Rules (GOHR), focusing on reinforcement learning agents trained to infer hidden rules from trial-and-error feedback, representation design, rule difficulty analysis, transfer learning, generalization, and pseudo-bot-assisted human learning analysis. The report focuses on the Transformer-based A2C framework, Feature-Centric and Object-Centric representations, experimental findings, and classification of human learning data. --- ### If It Walks Like an Arbitrage: Protocol-Agnostic Detection with Decidable Structural Equivalence Authors: Adam Khayam, Hamid Kolli, Mohamed Iguernlala, Çagdas Bozman Published: 2026-06-26 Categories: q-fin.CP, cs.CR, cs.LG arXiv: https://arxiv.org/abs/2608.20377v2 Whether a transaction performed an arbitrage, and by which route, is a question asked of its execution trace after the fact. We conjecture that such traces admit a normal form on which questions of this kind become queries, and we test it by building one and putting it to work. Each trace becomes an abstract syntax tree of token transfers, grouped by call- frame nesting. A term rewriting system of 16 rules reduces it. Rewriting terminates and carries exactly the transfers of the trace, whichever order the rules fire in. Under a deterministic kernel scanning the EVM-fixed trace order, every trace has a unique normal form, and the structural equivalence this induces on fund flows is decidable. Preservation, termination, soundness, uniqueness and decidability are mechanized in Rocq with zero admitted obligations. We report arbitrage detection in full: cycles emerge at the fixpoint and are read off the normal form with no protocol-specific patterns. Detection is the query we evaluate at scale; structural equivalence is a second query. The pipeline depends only on the standard ERC token and WETH ABIs, so the same binary runs unmodified on Arbitrum and BSC. We evaluate on two arbitrary block ranges, analysed in full with no transaction excluded: 220 000 Ethereum blocks against EigenPhi, a widely used MEV detection platform, and 1 000 shared blocks against ArbiNet, a graph neural network classifier. These are the only tools and label sets in this domain we were able to reuse. We report 469 801 confirmed arbitrages, overlapping 83.5% with EigenPhi and 81% with ArbiNet, together with 245 497 attempted arbitrages and 60 199 confirmed detections EigenPhi does not report. 99.2% follow from the fixpoint alone and are sound over the decoded transfers, and manual validation of 500 transactions finds no false positive among the confirmed. --- ### Geometry Is Not Robustness: A Trajectory-Level Study of PGD Evaluation Authors: Dhairysheel Durgule Published: 2026-06-26 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.14594v1 Projected Gradient Descent (PGD) is widely used to evaluate adversarial robustness, typically via final adversarial accuracy, which does not capture model behaviour throughout the attack. Recent work proposes trajectory-level diagnostics, such as loss evolution, gradient alignment, and steps-to-failure, for deeper insight into adversarial optimisation dynamics. However, whether these diagnostics reliably indicate robustness strength remains unclear. We conduct a trajectory-level investigation of PGD attacks on convolutional neural networks trained on Fashion-MNIST. We compare clean-trained and adversarially-trained models across multiple robustness regimes, using rigorous 20-step PGD evaluations with random initialisation and multiple restarts for robustness measurement, and single-initialisation trajectory recording for diagnostics. We record full PGD trajectories across 3000 clean-correct samples per model and analyse loss evolution, gradient alignment, and failure timing across attack iterations. Our results reveal a clear robustness hierarchy across models; however, trajectory metrics do not contribute equally to its identification. Mean loss trajectories and gradient alignment patterns appear quantitatively similar across adversarially-trained models with substantially different robust accuracies. In contrast, steps-to-failure distributions provide a clearer separation of robustness regimes, directly reflecting functional resistance to adversarial perturbation. These findings indicate that trajectory-level diagnostics describe optimisation geometry but do not independently measure adversarial robustness. Their interpretability depends on robustness regime, attack strength, and multi-metric evaluation. Trajectory-level analysis should be a complementary diagnostic tool, interpreted in context, rather than a replacement for standard robustness measurements. --- ### Don't Claim Benchmark-Oriented Optimization Improves General Coding Capability -- Diverse Evaluation Is Required Authors: Egor Shibaev, Vera Kudrevskaia, Timur Galimzyanov, Mikhail Evtikhiev, Ana Terna, Rastislav Rabatin, Timur Kudashev, Timofey Bryksin, Arina Puchkova, Patrik Bartak, Egor Bogomolov, Sergey Titov Published: 2026-06-26 Categories: cs.LG, cs.AI, cs.SE arXiv: https://arxiv.org/abs/2608.13566v1 Post-training papers, model cards, and blog posts often treat scores on a small set of coding benchmarks (e.g., SWE-bench and LiveCodeBench) as evidence of broad coding capability, both for research artifacts and user-facing systems. We argue that optimization for these benchmarks leads to measuring task-specific performance, creating a meaning gap between measured scores and claims of general coding ability. We examine this gap with a Django-based case study benchmark suite we create. Evaluating foundation models and checkpoints post-trained on SWE-bench trajectories, we find that benchmark rankings frequently fail to generalize. Post-trained checkpoints show little cross-task transfer, and SWE-bench optimization yields limited or no gains on our tasks or on LiveCodeBench. Similarly, fine-tuning on individual Django modalities fails to transfer. We conclude that a small number of benchmarks is insufficient for evaluating diverse models under benchmark optimization pressure. We encourage the community to use differentiated evaluation - holistic assessment for frontier models, multi-task suites for research, and human-in-the-loop studies for narrow task applications. Finally, we argue for creating a capability taxonomy and sustained benchmark maintenance, rather than one-off benchmark releases. Without reliable evaluation standards, engineers and researchers using LLMs and agents have to rely on insufficient evidence to make research, development, and deployment decisions. --- ### Challenges for Musical Education in the Age of AI and Digital Transformation Authors: Jean-Pierre Briot Published: 2026-06-26 Categories: cs.CY, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.05176v2 Music education has never been a static discipline. Each major technological shift has forced educators and institutions to reconsider what they teach, how they teach it, and why. We now stand at what may be the most consequential of such turning points. Three deeply intertwined transformations have been converging simultaneously: 1. The very nature of music has changed: how it is made, distributed, consumed, and valued; 2. The public for music has changed: listening habits are now shaped by streaming algorithms and the boundary between consumer and creator has blurred; 3. Music-making itself has changed: digital audio workstations (DAWs) have for two decades been reshaping compositional practice. In addition, generative AI has now irrupted, capable of producing complete, stylistically coherent musical pieces from a short text prompt. These changes are not independent of one another, and they all bear directly on musical education - both the content that must be taught, and the pedagogical tools and methods available to teach it. This paper attempts to map these challenges and to consider how education might adapt. Section 2 surveys the changes in various aspects of music (nature, production, public, economics). Section 3 examines the implications for education before Section 4 concludes. --- ### Challenges for Musical Education in the Age of AI and Digital Transformation Authors: Jean-Pierre Briot Published: 2026-06-26 Categories: cs.CY, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.05176v1 Music education has never been a static discipline. Each major technological shift has forced educators and institutions to reconsider what they teach, how they teach it, and why. We now stand at what may be the most consequential of such turning points. Three deeply intertwined transformations have been converging simultaneously: 1. The very nature of music has changed: how it is made, distributed, consumed, and valued; 2. The public for music has changed: listening habits are now shaped by streaming algorithms and the boundary between consumer and creator has blurred; 3. Music-making itself has changed: digital audio workstations (DAWs) have for two decades been reshaping compositional practice. In addition, generative AI has now irrupted, capable of producing complete, stylistically coherent musical pieces from a short text prompt. These changes are not independent of one another, and they all bear directly on musical education - both the content that must be taught, and the pedagogical tools and methods available to teach it. This paper attempts to map these challenges and to consider how education might adapt. Section 2 surveys the changes in various aspects of music (nature, production, public, economics). Section 3 examines the implications for education before Section 4 concludes. --- ### The Closing Window: How Governments Could Lose Their Ability to Restrain Advanced AI Authors: Peter Barnett Published: 2026-06-26 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2608.05173v1 As AI capabilities advance, AI systems will pose greater risks to national security and potentially humanity as a whole. Governments may eventually conclude that these risks warrant restraining AI development. This motivates the question: will governments still be able to restrain AI development in the future, should they want to do so? In this paper we analyze which world events and changes to the state of AI development would make future governance more difficult or even effectively impossible. Our analysis surfaces likely pathways that would lead to these difficulties, including hardware proliferation, continued algorithmic progress, and the release of catastrophically dangerous AI models. Due to the field's lack of understanding of AI development, it may be difficult or impossible to know when we will hit a "point of no return", and we therefore recommend a conservative approach. The window may be closing, but governments currently have an opportunity to preserve their optionality if they act soon. Our policy recommendations would enable governments to restrain AI development in the future, while imposing relatively small costs today. --- ### Estimating time spent on work tasks Authors: Stephane Hatgis-Kessell, Tomás Aguirre, Alexander Wan, Rishi Bommasani Published: 2026-06-26 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2608.05172v1 The task-based framework in economics models occupations as bundles of tasks. It is the standard lens for understanding how technology affects work: a new technology changes the cost or time each task requires and these task-level effects aggregate to occupation-level effects. We study how tasks should be weighted in this aggregation. Prior work has relied on idiosyncratic or ill-justified choices for task weights. While recent work suggests weighting tasks by time spent, existing time shares are either based on coarse ONET data not intended for this purpose or estimated via black-box language models. We address this gap by proposing a principled method for estimating time shares for nearly 18,000 tasks that constitute nearly all U.S. jobs. Our estimates factor a task's time into (i) the expected frequency of the task, derived from ONET, and (ii) the time to complete a single instance of it. To estimate the latter, we solve a constraint satisfaction problem based on pairwise comparisons elicited from language models about which tasks are longer per instance. We validate our estimates by characterizing the solution space of the constraint satisfaction problem and collecting data from workers for multiple occupations. We apply our time shares to analyze how AI exposes U.S. occupations and find that some prior results are sensitive to time weights. Accounting for the share of working time exposed to AI, rather than the share of tasks like prior work, widens the gap between the least and most exposed jobs: it lowers measured exposure for most occupations but raises it for the most exposed. Re-weighting by time also reshuffles 11 of the 25 occupations widely reported as most exposed to AI, shifting the top of the list away from clerical work and toward analytical roles. Time shares can serve as a general primitive for research and policy on the labor economy and the economics of technology. --- ### GLIDE: Guided Layerwise Hybrid Attention for Efficient LLM Inference Authors: Vimal William, Ravi Tandon, Jyotikrishna Dass Published: 2026-06-26 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2607.24788v1 As Large Language Models scale to increasingly long contexts, the memory I/O and computational overhead of the Key-Value (KV) cache during decoding emerges as the primary throughput bottleneck. To address this, we propose GLIDE, a Guided Layerwise Hybrid Attention that strategically integrates sliding-window softmax attention with linear recurrent aggregation. GLIDE is motivated by layer-wise heterogeneity: early layers exhibit high sensitivity to softmax removal, while deeper layers demonstrate redundancy and tolerate aggressive replacement by linear alternatives. Leveraging this insight, GLIDE introduces a layer-wise adaptive mechanism wherein each layer balances an efficient linear recurrence with a variable-sized softmax window. Unlike uniform hybrid approaches, GLIDE non-uniformly compresses the softmax footprint across the model, reducing aggregate KV cache I/O while preserving expressive power where most vital. Empirical evaluations demonstrate the GLIDE achieves superior performance-efficiency tradeoffs, reducing end-to-end latency for long-context generation without compromising quality. --- ### You Talkin to Me?: A Network Analysis of Gendered Speaker-Addressee Patterns in Film Screenplays Authors: Samin Khan, Camilla Griffiths, Shrikanth Narayanan, Dan Jurafsky, Sabyasachee Baruah Published: 2026-06-26 Categories: cs.CY, cs.CL arXiv: https://arxiv.org/abs/2607.22656v1 Objective: This paper investigates the gendered structure of speaker addressee relationships in film dialogue, asking not merely who speaks, but who is spoken to and how conversational dynamics unfold across gender lines. Methods: Using a manually annotated dataset of 4,600 directed dialogue events from 38 film screenplays, we apply network analysis, chi squared tests, paired statistical comparisons, and participation shift analysis across three studies. Key Findings: Male characters dominate as both speakers and addressees corpus wide, even in scenes with more women; cross gender dialogue is directionally symmetric on average but clustered at the film level; and same gender turns diffuse conversational attention while cross gender turns produce tighter dyadic reciprocation. Conclusion: Gender bias in film dialogue operates through the architecture of conversation itself, through exclusion from interaction and structural positioning as addressees, rather than through speaking time or within conversation directional imbalance alone. ---